Land Cover and Forest Type Classification by Values of Vegetation Indices and Forest Structure of Tropical Lowland Forests in Central Vietnam

Abstract

This paper aims to (i) optimize the application of multiple bands of satellite images for land cover classification by using random forest algorithms and (ii) assess correlations and regression of vegetation indices of a better-performed land cover classification image with vertical and horizontal structures of tropical lowland forests in Central Vietnam. In this study, we used Sentinel-2 and Landsat-8 to classify seven land cover classes of which three forest types were substratified as undisturbed, low disturbed, and disturbed forests where forest inventory of 90 plots, as ground-truth, was randomly sampled to measure forest tree parameters. A total of 3226 training points were sampled on seven land cover types. The performance of Landsat-8 showed out-of-bag error of 31.6%, overall accuracy of 68%, kappa of 67.5%, while Sentinel-2 showed out-of-bag error of 14.3% and overall accuracy of 85.7% and kappa of 83%. Ten vegetation indices of the better-performed image were extracted to find out (i) the correlation and regression of horizontal and vertical structures of trees and (ii) assess the variation values between ground-truthing plots and training sample plots in three forest types. The result of the t test on vegetation indices showed that six out of ten vegetation indices were significant at p<0.05. Seven vegetation indices had a correlation with the horizontal structure, but four vegetation indices, namely, Enhanced Vegetation Index, Perpendicular Vegetation Index, Difference Vegetation Index, and Transformed Normalized Difference Vegetation Index, had better correlations r = 0.66, 0.65, 0.65, 0.63 and regression results were of R2 = 0.44, 0.43, 0.43, and 0.40, respectively. The correlations of tree height were r = 0.46, 0.43, 0.43, and 0.49 and its regressions were of R2 = 0.21, 0.19, 0.18, and 0.24, respectively. The results show the possibility of using random forest algorithm with Sentinel-2 in forest type classification in line with vegetation indices application.

Floristic Composition and Life Forms of Plant Species in Nwamba Forest Reserve in Nigeria

“…The observation of a less dominant percentage of biological spectrums of hemicryptophytes and therophytes (Fig. 2) is in line with the study of Almouctar et al 33 , Trong et al 34 and Amjad 35 that aligned these life forms with vegetative zones of plant species. Also, the observed lower percentages of life form classes other than phanerophytes and chamaephytes reflects that environmental factor such as climate, drought and human influence might have aided positively or negatively in the less distribution and development of the species in their life form spectrum [36][37][38][39] .…”

Application of Remote Sensing in Monitoring Forest Cover Change and Carbon Dioxide Levels at Kisatchie National Forest of Louisiana

“…Vegetation indices contribute to land use planning and natural resources management and provide information to policymaking. (Nguyen Trong et al, 2020). VIs is widely employed in monitoring forest cover by employing reflectance values obtained from satellite data.…”

Vegetation Growth Analysis of UNESCO World Heritage Hyrcanian Forests Using Multi-Sensor Optical Remote Sensing Data

“…2.2.9. Modelling Sentinel-2-Derived TNPI Growth with Environmental Factors HF are mainly stretched in the longitudinal direction (Figure 1), thus, the 15 inscribed forest sites were divided into three forest zones (Figure 1): (i) the west forest (11,12,13,14,15), (ii) the east forest (1, 2, 3, 4, 5), and (iii) the middle forest (6,7,8,9,10). We randomly generated 100 sampling points within each forest shapefile and then extracted raster data values of elevation, LST, precipitation, and Sentinel-2-based TNPI Growth using the procedures described in Section 2.2.8.…”

“…Optical satellite remote sensing provides information for studying large-scale forest changes in near real-time with a comparable spatial and higher temporal resolutions compared with field surveys, which are often constrained by logistics and difficult-toaccess terrain. Among the available methods, those based on broadband vegetation indices (VIs) derived from multispectral data have been widely used [5][6][7] for vegetation classification [8], phenological monitoring [9], change detection [10], and the retrieval of Remote Sens. 2021, 13, 3965 2 of 17 forest biophysical and structural attributes [11].…”